SaaSBench (Engineering) - Customer & Growth: leaderboard

Metric: Task score (%; pass@1, mean over the seven Customer & Growth tasks of the share of each task's validation-DAG max score earned; agent builds and deploys an enterprise SaaS system from a PRD). Source: arxiv.org. Saturation forecast: Around July 2028. 16 models tracked.

Top models

#ModelScore
1Claude Opus 4.7 (Claude Code)21.51

Interactive version: theaggregate.ai/benchmark?slug=saasbench-engineering-customer-growth · How It Works · Data refreshed daily, snapshot 2026-09-26.